US Patent Application 18136614. IMAGE PROCESSING APPARATUS AND OPERATING METHOD THEREOF simplified abstract
Contents
IMAGE PROCESSING APPARATUS AND OPERATING METHOD THEREOF
Organization Name
Inventor(s)
Youngchan Song of Suwon-si (KR)
IMAGE PROCESSING APPARATUS AND OPERATING METHOD THEREOF - A simplified explanation of the abstract
This abstract first appeared for US patent application 18136614 titled 'IMAGE PROCESSING APPARATUS AND OPERATING METHOD THEREOF
Simplified Explanation
The patent application describes an image processing apparatus that uses a neural network to process images.
- The apparatus includes a memory and a processor.
- The processor executes instructions stored in the memory.
- The apparatus obtains first feature data based on a first image.
- It performs first image processing on the first feature data to obtain pieces of second feature data corresponding to specific areas of the first image.
- These specific areas are defined as first areas and consist of a certain number of pixels.
- The apparatus also obtains third feature data based on the first image.
- It performs second image processing on the third feature data to obtain pieces of fourth feature data corresponding to different areas of the first image.
- These different areas are defined as second areas and consist of a greater number of pixels compared to the first areas.
- Finally, the apparatus generates a second image using the pieces of second feature data and the pieces of fourth feature data.
Original Abstract Submitted
An image processing apparatus for processing an image by using one neural network, includes: a memory storing one instruction; and one processor configured to execute the one instruction to: obtain first feature data, based on a first image, obtain pieces of second feature data corresponding to first areas of the first image by performing first image processing on the first feature data, the first areas comprising a first number of pixels, obtain third feature data, based on the first image, obtain pieces of fourth feature data corresponding to second areas of the first image, by performing second image processing on the third feature data, the second areas comprising a second number of pixels that is greater than the first number, and generate a second image, based on the pieces of second feature data and the pieces of fourth feature data.
